Modern large language models (LLMs) like ChatGPT have shown remarkable performance on general language tasks but still struggle on complex reasoning tasks, which drives the research on cognitive behaviors of LLMs to explore human-like problem-solving strategies. Along this direction, one representative strategy is self-reflection, which asks an LLM to refine the solution with the feedback generated by itself iteratively. However, our study shows that such reflection-style methods suffer from the Degeneration-of-Thought (DoT) problem: once the LLM has established confidence in its solutions, it is unable to generate novel thoughts later through reflection even if its initial stance is incorrect. To address the DoT problem, we propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of “tit for tat” and a judge manages the debate process to obtain a final solution. Clearly, our MAD framework encourages divergent thinking in LLMs which would be helpful for tasks that require deep levels of contemplation. Experiment results on two challenging datasets, commonsense machine translation and counter-intuitive arithmetic reasoning, demonstrate the effectiveness of our MAD framework. Extensive analyses suggest that the adaptive break of debate and the modest level of “tit for tat” state are required for MAD to obtain good performance. Moreover, we find that LLMs might not be a fair judge if different LLMs are used for agents.

The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game descriptions and generate game-play processes. The IDGE allows users to create games simply by natural language instructions, which significantly lowers the barrier for game development. We approach the learning process for IDGEs as a Next State Prediction task, wherein the model autoregressively predicts the game states given player actions. The computation of game states must be precise; otherwise, slight errors could corrupt the game-play experience. This is challenging because of the gap between stability and diversity. To address this, we train the IDGE in a curriculum manner that progressively increases its exposure to complex scenarios.Our initial progress lies in developing an IDGE for Poker, which not only supports a wide range of poker variants but also allows for highly individualized new poker games through natural language inputs. This work lays the groundwork for future advancements in transforming how games are created and played.

Multimodal large language models (MLLMs) are flourishing, but mainly focus on images with less attention than videos, especially in sub-fields such as prompt engineering, video chain-of-though (CoT), and instruction tuning on videos. Therefore, we try to explore the collection of CoT datasets in videos to lead to video OpenQA and improve the reasoning ability of MLLMs. Unfortunately, making such video CoT datasets is not an easy task. Given that human annotation is too cumbersome and expensive, while machine-generated is not reliable due to the hallucination issue, we develop an automatic annotation tool that combines machine and human experts, under the active learning paradigm. Active learning is an interactive strategy between the model and human experts, in this way, the workload of human labeling can be reduced and the quality of the dataset can be guaranteed. With the help of the automatic annotation tool, we strive to contribute three datasets, namely VideoCoT, TopicQA, TopicCoT. Furthermore, we propose a simple but effective benchmark based on the collected datasets, which exploits CoT to maximize the complex reasoning capabilities of MLLMs. Extensive experiments demonstrate the effectiveness our solution, and we will release our source codes and datasets to facilitate the research community.

Model fusing has always been an important topic, especially in an era where large language models (LLM) and multi-modal language models (MLM) with different architectures, parameter sizes and training pipelines, are being created all the time. In this work, we propose a post-hoc framework, aiming at fusing heterogeneous models off-the-shell, which we call likelihood composition, and the basic idea is to compose multiple models’ likelihood distribution when doing a multi-choice visual-question-answering task. Here the core concept, likelihood, is actually the log-probability of the candidate answer. In likelihood composition, we introduce some basic operations: debias, highlight, majority-vote and ensemble. By combining (composing) these basic elements, we get the mixed composition methods: mix-composition. Through conducting comprehensive experiments on 9 VQA datasets and 10 MLMs, we prove the effectiveness of mix-composition compared with simple ensemble or majority-vote methods. In this framework, people can propose new basic composition methods and combine them to get the new mixed composition methods. We hope our proposed likelihood composition can provide a new perspective of fusing heterogeneous models and inspire the exploration under this framework.

While extensive work has examined the explicit and implicit biases in large language models (LLMs), little research explores the relation between these two types of biases. This paper presents a comparative study of the explicit and implicit biases in LLMs grounded in social psychology. Social psychology distinguishes between explicit and implicit biases by whether the bias can be self-recognized by individuals. Aligning with this conceptualization, we propose a self-evaluation-based two-stage measurement of explicit and implicit biases within LLMs. First, the LLM is prompted to automatically fill templates with social targets to measure implicit bias toward these targets, where the bias is less likely to be self-recognized by the LLM. Then, the LLM is prompted to self-evaluate the templates filled by itself to measure explicit bias toward the same targets, where the bias is more likely to be self-recognized by the LLM. Experiments conducted on state-of-the-art LLMs reveal human-like inconsistency between explicit and implicit occupational gender biases. This work bridges a critical gap where prior studies concentrate solely on either explicit or implicit bias. We advocate that future work highlight the relation between explicit and implicit biases in LLMs.

Emotion recognition in conversation (ERC) is a field that aims to classify the emotion of each utterance within conversational contexts. This presents significant challenges, particularly in handling emotional ambiguity across various speakers and contextual factors. Existing ERC approaches have primarily focused on modeling conversational contexts while incorporating only superficial speaker attributes such as names, memories, and interactions. Recent works introduce personality as an essential deep speaker factor for emotion recognition, but relies on static personality, overlooking dynamic variability during conversations. Advances in personality psychology conceptualize personality as dynamic, proposing that personality states can change across situations. In this paper, we introduce ERC-DP, a novel model considering the dynamic personality of speakers during conversations. ERC-DP accounts for past utterances from the same speaker as situation impacting dynamic personality. It combines personality modeling with prompt design and fine-grained classification modules. Through a series of comprehensive experiments, ERC-DP demonstrates superior performance on three benchmark conversational datasets.

Sexism has become a growing concern on social media platforms as it impacts the health of the internet and can have negative impacts on society. This paper describes the coco system that participated in SemEval-2023 Task 10, Explainable Detection of Online Sexism (EDOS), which aims at sexism detection in various settings of natural language understanding. We develop a novel neural framework for sexism detection and misogyny that can combine text representations obtained using pre-trained language model models such as Bidirectional Encoder Representations from Transformers and using BiLSTM architecture to obtain the local and global semantic information. Further, considering that the EDOS dataset is relatively small and extremely unbalanced, we conducted data augmentation and introduced two datasets in the field of sexism detection. Moreover, we introduced Focal Loss which is a loss function in order to improve the performance of processing imbalanced data classification. Our system achieved an F1 score of 78.95\% on Task A - binary sexism.

Writing assistants are valuable tools that can help writers improve their writing skills. We introduce Effidit (Efficient and Intelligent Editing), a digital writing assistant that facilitates users to write higher-quality text more efficiently through the use of Artificial Intelligence (AI) and Natural Language Processing (NLP) technologies. We significantly expand the capacities of a writing assistantby providing functions in three modules: text completion, hint recommendation, and writing refinement. Based on the above efforts, Effidit can efficiently assist users in creating their own text. Effidit has been deployed to several Tencent products and publicly released at https://effidit.qq.com/.

Commonsense generation aims to generate a plausible sentence containing all given unordered concept words. Previous methods focusing on this task usually directly concatenate these words as the input of a pre-trained language model (PLM). However, in PLMs’ pre-training process, the inputs are often corrupted sentences with correct word order. This input distribution discrepancy between pre-training and fine-tuning makes the model difficult to fully utilize the knowledge of PLMs. In this paper, we propose a two-stage framework to alleviate this issue. Firstly, in pre-training stage, we design a new format of input to endow PLMs the ability to deal with masked sentences with incorrect word order. Secondly, during fine-tuning, we insert the special token [MASK] between two consecutive concept words to make the input distribution more similar to the input distribution in pre-training. We conduct extensive experiments and provide thorough analysis to demonstrate the effectiveness of our proposed method.

Patients who effectively manage their symptoms often demonstrate higher levels of engagement in conversations and interventions with healthcare practitioners. This engagement is multifaceted, encompassing cognitive and social dimensions. Consequently, it is crucial for AI systems to understand the engagement in natural conversations between patients and practitioners to better contribute toward patient care. In this paper, we present a novel dataset (MedNgage), which consists of patient-nurse conversations about cancer symptom management. We manually annotate the dataset with a novel framework of categories of patient engagement from two different angles, namely: i) socio-affective engagement (3.1K spans), and ii) cognitive engagement (1.8K spans). Through statistical analysis of the data that is annotated using our framework, we show a positive correlation between patient symptom management outcomes and their engagement in conversations. Additionally, we demonstrate that pre-trained transformer models fine-tuned on our dataset can reliably predict engagement categories in patient-nurse conversations. Lastly, we use LIME (Ribeiro et al., 2016) to analyze the underlying challenges of the tasks that state-of-the-art transformer models encounter. The de-identified data is available for research purposes upon request.

In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals remains a considerable challenge due to the complexities of character representation and the lack of comprehensive annotations. In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry Potter series and is annotated with vital background information, including dialogue scenes, speakers, character relationships, and attributes. These extensive annotations may empower LLMs to unlock character-driven dialogue capabilities. Furthermore, it can serve as a universal benchmark for evaluating how well can a LLM aligning with a specific character. We benchmark LLMs on HPD using both fine-tuning and in-context learning settings. Evaluation results reveal that although there is substantial room for improvement in generating high-quality, character-aligned responses, the proposed dataset is valuable in guiding models toward responses that better align with the character of Harry Potter.

We present PandaGPT, an approach to emPower large lANguage moDels with visual and Auditory instruction-following capabilities. Our pilot experiments show that PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questions about audios. More interestingly, PandaGPT can take multimodal inputs simultaneously and compose their semantics naturally. For example, PandaGPT can connect how objects look in an image/video and how they sound in an audio. To do so, PandaGPT combines the multimodal encoders from ImageBind and the large language models from Vicuna. Notably, only aligned image-text pairs are required for the training of PandaGPT. Thanks to the strong capability of ImageBind in embedding data from different modalities into the same space, PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU). We hope that PandaGPT serves as an initial step toward building AGI that can perceive and understand inputs in different modalities holistically, as we humans do.

This paper describes our proposed framework for the 10 text classification tasks of Task 1a, 2a, 2b, 3a, 4, 5, 6, 7, 8, and 9, in the Social Media Mining for Health (SMM4H) 2022. According to the pre-trained BERT-based models, various techniques, including regularized dropout, focal loss, exponential moving average, 5-fold cross-validation, ensemble prediction, and pseudo-labeling, are applied for further formulating and improving the generalization performance of our framework. In the evaluation, the proposed framework achieves the 1st place in Task 3a with a 7% higher F1-score than the median, and obtains a 4% higher averaged F1-score than the median in all participating tasks except Task 1a.

Maintaining a consistent persona is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated personalized dialogue datasets is still a barrier towards training robust and consistent persona-based dialogue models. This work shows how this challenge can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understanding. In particular, to learn the ability of consistency understanding from large-scale non-dialogue inference data, we train the second decoder in an unlikelihood manner. Under different limited data settings, both automatic and human evaluations demonstrate that the proposed model outperforms strong baselines in response quality and persona consistency.

We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that models trained with random negative samples are not ideal in real-world scenarios, we propose a hierarchical curriculum learning framework that trains the matching model in an “easy-to-difficult” scheme. Our learning framework consists of two complementary curricula: (1) corpus-level curriculum (CC); and (2) instance-level curriculum (IC). In CC, the model gradually increases its ability in finding the matching clues between the dialogue context and a response candidate. As for IC, it progressively strengthens the model’s ability in identifying the mismatching information between the dialogue context and a response candidate. Empirical studies on three benchmark datasets with three state-of-the-art matching models demonstrate that the proposed learning framework significantly improves the model performance across various evaluation metrics.

Prior work has proved that Translation Memory (TM) can boost the performance of Neural Machine Translation (NMT). In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search for memory retrieval, we propose a new framework that uses monolingual memory and performs learnable memory retrieval in a cross-lingual manner. Our framework has unique advantages. First, the cross-lingual memory retriever allows abundant monolingual data to be TM. Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal. Experiments show that the proposed method obtains substantial improvements. Remarkably, it even outperforms strong TM-augmented NMT baselines using bilingual TM. Owning to the ability to leverage monolingual data, our model also demonstrates effectiveness in low-resource and domain adaptation scenarios.

Non-autoregressive generation (NAG) has recently attracted great attention due to its fast inference speed. However, the generation quality of existing NAG models still lags behind their autoregressive counterparts. In this work, we show that BERT can be employed as the backbone of a NAG model for a greatly improved performance. Additionally, we devise two mechanisms to alleviate the two common problems of vanilla NAG models: the inflexibility of prefixed output length and the conditional independence of individual token predictions. To further strengthen the speed advantage of the proposed model, we propose a new decoding strategy, ratio-first, for applications where the output lengths can be approximately estimated beforehand. For a comprehensive evaluation, we test the proposed model on three text generation tasks, including text summarization, sentence compression and machine translation. Experimental results show that our model significantly outperforms existing non-autoregressive baselines and achieves competitive performance with many strong autoregressive models. In addition, we also conduct extensive analysis experiments to reveal the effect of each proposed component.

Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases. However, the lacking of parallel corpus hinders the ability of these inductive learning methods on this task. As a result, it is likely to cause severe inconsistent style expressions, like ‘the salad is rude’. To tackle this problem, we propose a novel transductive learning approach in this paper, based on a retrieval-based context-aware style representation. Specifically, an attentional encoder-decoder with a retriever framework is utilized. It involves top-K relevant sentences in the target style in the transfer process. In this way, we can learn a context-aware style embedding to alleviate the above inconsistency problem. In this paper, both sparse (BM25) and dense retrieval functions (MIPS) are used, and two objective functions are designed to facilitate joint learning. Experimental results show that our method outperforms several strong baselines. The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.

Word similarity is widely used in machine learning applications like searching engine and recommendation. Measuring the changing meaning of the same word between two different sentences is not only a way to handle complex features in word usage (such as sentence syntax and semantics), but also an important method for different word polysemy modeling. In this paper, we present the methodology proposed by team Ferryman. Our system is based on the Bidirectional Encoder Representations from Transformers (BERT) model combined with term frequency-inverse document frequency (TF-IDF), applying the method on the provided datasets called CoSimLex, which covers four different languages including English, Croatian, Slovene, and Finnish. Our team Ferryman wins the the first position for English task and the second position for Finnish in the subtask 1.

The main purpose of this article is to state the effect of using different methods and models for counterfactual determination and detection of causal knowledge. Nowadays, counterfactual reasoning has been widely used in various fields. In the realm of natural language process(NLP), counterfactual reasoning has huge potential to improve the correctness of a sentence. In the shared Task 5 of detecting counterfactual in SemEval 2020, we pre-process the officially given dataset according to case conversion, extract stem and abbreviation replacement. We use last-5 bidirectional encoder representation from bidirectional encoder representation from transformer (BERT)and term frequency–inverse document frequency (TF-IDF) vectorizer for counterfactual detection. Meanwhile, multi-sample dropout and cross validation are used to improve versatility and prevent problems such as poor generosity caused by overfitting. Finally, our team Ferryman ranked the 8th place in the sub-task 1 of this competition.

Natural language processing (NLP) has been applied to various fields including text classification and sentiment analysis. In the shared task of assessing the funniness of edited news headlines, which is a part of the SemEval 2020 competition, we preprocess datasets by replacing abbreviation, stemming words, then merge three models including Light Gradient Boosting Machine (LightGBM), Long Short-Term Memory (LSTM), and Bidirectional Encoder Representation from Transformer (BERT) by taking the average to perform the best. Our team Ferryman wins the 9th place in Sub-task 1 of Task 7 - Regression.

Indiscriminately posting offensive remarks on social media may promote the occurrence of negative events such as violence, crime, and hatred. This paper examines different approaches and models for solving offensive tweet classification, which is a part of the OffensEval 2020 competition. The dataset is Offensive Language Identification Dataset (OLID), which draws 14,200 annotated English Tweet comments. The main challenge of data preprocessing is the unbalanced class distribution, abbreviation, and emoji. To overcome these issues, methods such as hashtag segmentation, abbreviation replacement, and emoji replacement have been adopted for data preprocessing approaches. The main task can be divided into three sub-tasks, and are solved by Term Frequency–Inverse Document Frequency(TF-IDF), Bidirectional Encoder Representation from Transformer (BERT), and Multi-dropout respectively. Meanwhile, we applied different learning rates for different languages and tasks based on BERT and non-BERTmodels in order to obtain better results. Our team Ferryman ranked the 18th, 8th, and 21st with F1-score of 0.91152 on the English Sub-task A, Sub-task B, and Sub-task C, respectively. Furthermore, our team also ranked in the top 20 on the Sub-task A of other languages.

While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well. This results in poor quantity representations and incorrect solution expressions. In this paper, we propose Graph2Tree, a novel deep learning architecture that combines the merits of the graph-based encoder and tree-based decoder to generate better solution expressions. Included in our Graph2Tree framework are two graphs, namely the Quantity Cell Graph and Quantity Comparison Graph, which are designed to address limitations of existing methods by effectively representing the relationships and order information among the quantities in MWPs. We conduct extensive experiments on two available datasets. Our experiment results show that Graph2Tree outperforms the state-of-the-art baselines on two benchmark datasets significantly. We also discuss case studies and empirically examine Graph2Tree’s effectiveness in translating the MWP text into solution expressions.

Maintaining a consistent personality in conversations is quite natural for human beings, but is still a non-trivial task for machines. The persona-based dialogue generation task is thus introduced to tackle the personality-inconsistent problem by incorporating explicit persona text into dialogue generation models. Despite the success of existing persona-based models on generating human-like responses, their one-stage decoding framework can hardly avoid the generation of inconsistent persona words. In this work, we introduce a three-stage framework that employs a generate-delete-rewrite mechanism to delete inconsistent words from a generated response prototype and further rewrite it to a personality-consistent one. We carry out evaluations by both human and automatic metrics. Experiments on the Persona-Chat dataset show that our approach achieves good performance.

Emotion recognition in conversation (ERC) is an important topic for developing empathetic machines in a variety of areas including social opinion mining, health-care and so on. In this paper, we propose a method to model ERC task as sequence tagging where a Conditional Random Field (CRF) layer is leveraged to learn the emotional consistency in the conversation. We employ LSTM-based encoders that capture self and inter-speaker dependency of interlocutors to generate contextualized utterance representations which are fed into the CRF layer. For capturing long-range global context, we use a multi-layer Transformer encoder to enhance the LSTM-based encoder. Experiments show that our method benefits from modeling the emotional consistency and outperforms the current state-of-the-art methods on multiple emotion classification datasets.

Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans. Existing studies on improving attribute consistency mainly explored how to incorporate attribute information in the responses, but few efforts have been made to identify the consistency relations between response and attribute profile. To facilitate the study of profile consistency identification, we create a large-scale human-annotated dataset with over 110K single-turn conversations and their key-value attribute profiles. Explicit relation between response and profile is manually labeled. We also propose a key-value structure information enriched BERT model to identify the profile consistency, and it gained improvements over strong baselines. Further evaluations on downstream tasks demonstrate that the profile consistency identification model is conducive for improving dialogue consistency.

Response selection plays a vital role in building retrieval-based conversation systems. Despite that response selection is naturally a learning-to-rank problem, most prior works take a point-wise view and train binary classifiers for this task: each response candidate is labeled either relevant (one) or irrelevant (zero). On the one hand, this formalization can be sub-optimal due to its ignorance of the diversity of response quality. On the other hand, annotating grayscale data for learning-to-rank can be prohibitively expensive and challenging. In this work, we show that grayscale data can be automatically constructed without human effort. Our method employs off-the-shelf response retrieval models and response generation models as automatic grayscale data generators. With the constructed grayscale data, we propose multi-level ranking objectives for training, which can (1) teach a matching model to capture more fine-grained context-response relevance difference and (2) reduce the train-test discrepancy in terms of distractor strength. Our method is simple, effective, and universal. Experiments on three benchmark datasets and four state-of-the-art matching models show that the proposed approach brings significant and consistent performance improvements.

Several deep learning models have been proposed for solving math word problems (MWPs) automatically. Although these models have the ability to capture features without manual efforts, their approaches to capturing features are not specifically designed for MWPs. To utilize the merits of deep learning models with simultaneous consideration of MWPs’ specific features, we propose a group attention mechanism to extract global features, quantity-related features, quantity-pair features and question-related features in MWPs respectively. The experimental results show that the proposed approach performs significantly better than previous state-of-the-art methods, and boost performance from 66.9% to 69.5% on Math23K with training-test split, from 65.8% to 66.9% on Math23K with 5-fold cross-validation and from 69.2% to 76.1% on MAWPS.

Traditional generative dialogue models generate responses solely from input queries. Such information is insufficient for generating a specific response since a certain query could be answered in multiple ways. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. For a given query, similar dialogues are retrieved from the entire training data and considered as an additional knowledge source. While the use of retrieval may harvest extensive information, the generative models could be overwhelmed, leading to unsatisfactory performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-to-response paradigm. At first, a skeleton is extracted from the retrieved dialogues. Then, both the generated skeleton and the original query are used for response generation via a novel response generator. Experimental results show that our approach significantly improves the informativeness of the generated responses

In multi-turn dialogue, utterances do not always take the full form of sentences. These incomplete utterances will greatly reduce the performance of open-domain dialogue systems. Restoring more incomplete utterances from context could potentially help the systems generate more relevant responses. To facilitate the study of incomplete utterance restoration for open-domain dialogue systems, a large-scale multi-turn dataset Restoration-200K is collected and manually labeled with the explicit relation between an utterance and its context. We also propose a “pick-and-combine” model to restore the incomplete utterance from its context. Experimental results demonstrate that the annotated dataset and the proposed approach significantly boost the response quality of both single-turn and multi-turn dialogue systems.

End-to-end sequence generation is a popular technique for developing open domain dialogue systems, though they suffer from the safe response problem. Researchers have attempted to tackle this problem by incorporating generative models with the returns of retrieval systems. Recently, a skeleton-then-response framework has been shown promising results for this task. Nevertheless, how to precisely extract a skeleton and how to effectively train a retrieval-guided response generator are still challenging. This paper presents a novel framework in which the skeleton extraction is made by an interpretable matching model and the following skeleton-guided response generation is accomplished by a separately trained generator. Extensive experiments demonstrate the effectiveness of our model designs.

Comments of online articles provide extended views and improve user engagement. Automatically making comments thus become a valuable functionality for online forums, intelligent chatbots, etc. This paper proposes the new task of automatic article commenting, and introduces a large-scale Chinese dataset with millions of real comments and a human-annotated subset characterizing the comments’ varying quality. Incorporating the human bias of comment quality, we further develop automatic metrics that generalize a broad set of popular reference-based metrics and exhibit greatly improved correlations with human evaluations.

Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving. Despite its simplicity, a drawback still remains: a math word problem can be correctly solved by more than one equations. This non-deterministic transduction harms the performance of maximum likelihood estimation. In this paper, by considering the uniqueness of expression tree, we propose an equation normalization method to normalize the duplicated equations. Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving. We find that each model has its own specialty in solving problems, consequently an ensemble model is then proposed to combine their advantages. Experiments on dataset Math23K show that the ensemble model with equation normalization significantly outperforms the previous state-of-the-art methods.

This paper presents a deep neural solver to automatically solve math word problems. In contrast to previous statistical learning approaches, we directly translate math word problems to equation templates using a recurrent neural network (RNN) model, without sophisticated feature engineering. We further design a hybrid model that combines the RNN model and a similarity-based retrieval model to achieve additional performance improvement. Experiments conducted on a large dataset show that the RNN model and the hybrid model significantly outperform state-of-the-art statistical learning methods for math word problem solving.